Python SDK - DecimalAI

The Python SDK is the primary way to integrate DecimalAI into your agent code. It wraps most of the public REST API (see REST-only endpoints for the gaps), auto-instruments 9 agent framework integrations plus 3 direct LLM provider SDKs (OpenAI, Anthropic, Google) — including native plugins for Google ADK and Anthropic’s Claude Agent SDK — and ships zero-config helpers for tracing, evaluation, and dataset export.

pip install decimalai

import decimalai
decimalai.init(api_key="dai_sk_...", openai_agents=True)
# OpenAI Agents SDK calls are now traced.

Sections

Init & Setup

decimalai.init(), environment variables, framework flags.

Tracing

@trace, start_trace, log_llm_call, log_tool_call, @tool.

Manifests

register_manifest, flush_manifest_for_ci.

Evaluations

eval, score, get_eval_breakdown, batch_eval, @eval, external imports.

Replay & Experiments

get_replay_prompts, create_replay_batch, get_replay_batch.

Datasets & Training

pull_dataset, push_to_hub, load_hf_dataset.

Framework Instrumentation

8 framework integrations — OpenAI Agents, LangChain, LlamaIndex, Pydantic AI, CrewAI, generic OTel, plus native plugins for Google ADK and Anthropic Claude Agent SDK.

Skills

Sync from disk, pull from platform, SkillRouter CRUD.

Complete API Summary

Top-level functions (in `decimalai`)

Grouped by surface. Every function below is importable directly from decimalai.

Tracing

Method	Description
`init()`	Initialize SDK and auto-instrument frameworks.
`@trace()`	Decorator to trace a function as an agent run.
`start_trace()`	Context manager for manual trace boundaries.
`log_llm_call()`	Log an LLM call inside a trace.
`log_tool_call()`	Log a tool call inside a trace.
`@tool`	Decorator to register a tracked tool.
`send()`	Send a fully-constructed trace payload.

Manifests

Method	Description
`register_manifest()`	Explicitly register agent configuration.
`flush_manifest_for_ci()`	Capture and write the manifest ID for the regression-check Action.

Evaluations

Method	Description
`eval()`	Pushes a single named score to a trace (alias of `score()`). The custom-evaluator decorator is `@decimalai.evals.eval`, not this top-level function.
`score()`	Push a single named score to a trace.
`batch_eval()`	Apply evaluators across multiple traces in parallel.
`get_eval_breakdown()`	Get full eval breakdown for a trace.
`push_deepeval_results()`	Import DeepEval scores.
`push_langsmith_scores()`	Import LangSmith feedback as eval scores.
`push_custom_scores()`	Push scores from any source.

Datasets

Method	Description
`pull_dataset()`	Download a dataset version to a local JSONL/Parquet file (returns a summary dict).
`push_to_hub()`	Push a dataset to HuggingFace Hub.
`load_hf_dataset()`	Load a dataset version directly as an in-memory `datasets.Dataset` (no file).

Replay

Method	Description
`get_replay_prompts()`	Download stale prompts for replay.
`create_replay_batch()`	Create a batch of replay tasks.
`get_replay_batch()`	Check replay batch progress.
`submit_replay_result()`	Submit a replayed trace result.
`repair_preview()`	Preview mechanical repair rules for a manifest transition.
`repair_apply()`	Apply repair rules for a manifest transition.

Framework instrumentation (subpackages)

9 framework integrations — eight ship a subpackage; CrewAI is flag-only (see below). Google ADK and Anthropic’s Claude Agent SDK use native plugins (not OTel).

Module	Function	Use it for
`decimalai.langchain`	`instrument()`	LangChain / LangGraph callbacks
`decimalai.openai_agents`	`instrument(agent=...)`	OpenAI Agents SDK — pass the Agent object for full schema introspection
`decimalai.llamaindex`	`instrument()`	LlamaIndex span handler
`decimalai.adk`	`instrument()`	Google ADK — native plugin (Gemini-native)
`decimalai.claude_agent_sdk`	`instrument()`	Anthropic Claude Agent SDK — native plugin
`decimalai.pydantic_ai`	`instrument(enable_skill_loader=True)`	Pydantic AI skill loader + `load_skill` tool
`decimalai.otel`	`instrument()`	Generic OpenTelemetry GenAI span exporter

These entry points were called install() in 0.10.0 and earlier. They were renamed to instrument() in 0.10.2 — same arguments, same behaviour — because install had come to mean something else entirely: adding a skill to your workspace. install() still works and emits a DeprecationWarning. See Vocabulary.Not to be confused with SkillRouter.install(), which is the skill operation and keeps its name.

There is no decimalai.crewai subpackage — CrewAI rides the generic OTel rail: decimalai.init(crewai=True) is a convenience alias for the OTel exporter (see Frameworks).

Class-based clients

Class	Use it for
`SkillRouter` (from `decimalai`)	Registry + skill lifecycle: `fork` (workspace copy), `install` (fork + write to disk), `preview` (read-only snapshot), `create_skill`, `list_skills`, `get_skill`, `update_skill`, `delete_skill`, `sync_skills`, `list_versions`, `get_menu`, `smart_route`, `get_menu_prompt`, `build_prompt_fragment` (fragment + routing record for manual prompt assembly), `load_skill` (budgeted on-demand body, counted as delivered + activated), `get_skill_body` (raw body fetch, server-side trim), `export_to_disk`, `pull_missing`.

Body delivery is budgeted per turn via four constructor kwargs, mirroring the backend defaults: max_loaded_bodies=3 (max distinct bodies per turn), body_token_budget=6000 (estimated-token ceiling across loaded bodies), per_body_char_limit=8192 (per-body trim), body_load_deadline_s=20.0 (wall-clock cutoff after which further loads are refused).

Two inject flags, two scopes — they are not spellings of the same thing. SkillRouter(inject_body=True) configures that router instance to include routed bodies in its prompt fragment. decimalai.init(inject_skill_body=True) (env: DECIMALAI_INJECT_SKILL_BODY=1) is global adapter config — it overrides the per-adapter default for budgeted body injection (on for langchain / anthropic / adk, which have no tool loop; off for openai_agents / pydantic_ai, which load bodies through load_skill; SDK 0.12.0+). Setting one does not set the other.

REST-only endpoints

For endpoints that don’t yet have a top-level SDK wrapper (list_datasets, get_trace_stats, get_manifest, compatibility policy set, etc.), use httpx directly against the REST API:

import httpx

resp = httpx.get(
    "https://api.decimal.ai/api/v1/datasets",
    headers={"Authorization": "Bearer dai_sk_..."},
)
resp.raise_for_status()

See the API Reference for the full endpoint registry.

​Sections

Init & Setup

Tracing

Manifests

Evaluations

Replay & Experiments

Datasets & Training

Framework Instrumentation

Skills

​Complete API Summary

​Top-level functions (in decimalai)

​Framework instrumentation (subpackages)

​Class-based clients

​REST-only endpoints

Sections

Complete API Summary

Top-level functions (in `decimalai`)

Framework instrumentation (subpackages)

Class-based clients

REST-only endpoints